def test_unused_validator_fails_validation():
source = LocalFile('vladiate/examples/vampires.csv')
validators = {
'Column A': [UniqueValidator()],
'Column B': [SetValidator(['Vampire', 'Not A Vampire'])],
'Column C': [FloatValidator()]
}
assert not Vlad(source=source, validators=validators).validate()
def test_unused_validator_fails_validation():
source = LocalFile("vladiate/examples/vampires.csv")
validators = {
"Column A": [UniqueValidator()],
"Column B": [SetValidator(["Vampire", "Not A Vampire"])],
"Column C": [FloatValidator()],
}
assert not Vlad(source=source, validators=validators).validate()
def perform_batch_validation(filename):
validators = {
'FILENAME': [NotEmptyValidator()],
'SEQ': [SetValidator(valid_set=["*..*", "*.*"])],
'COMPOUND_NAME': [NotEmptyValidator()],
'MOLECULEMASS': [FloatValidator()],
'INSTRUMENT': [
SetValidator(valid_set=[
"qTof", "QQQ", "Ion Trap", "Hybrid FT", "Orbitrap", "ToF"
])
],
'IONSOURCE':
[SetValidator(valid_set=["LC-ESI", "DI-ESI", "EI", "APCI", "ESI"])],
'EXTRACTSCAN': [IntValidator()],
'SMILES': [],
'INCHI': [],
'INCHIAUX': [],
'CHARGE': [IntValidator()],
'IONMODE': [SetValidator(valid_set=["Positive", "Negative"])],
'PUBMED': [NotEmptyValidator()],
'ACQUISITION': [
SetValidator(valid_set=[
"Crude", "Lysate", "Commercial", "Isolated", "Other"
])
],
'EXACTMASS': [FloatValidator()],
'DATACOLLECTOR': [NotEmptyValidator()],
'ADDUCT': [NotEmptyValidator()],
'INTEREST': [],
'LIBQUALITY': [SetValidator(valid_set=["1", "2", "3"])],
'GENUS': [],
'SPECIES': [],
'STRAIN': [],
'CASNUMBER': [NotEmptyValidator()],
'PI': [NotEmptyValidator()]
}
my_validator = Vlad(source=LocalFile(filename),
delimiter="\t",
ignore_missing_validators=True,
validators=validators)
passes_validation = my_validator.validate()
errors_list = []
for column in my_validator.failures:
for line_number in my_validator.failures[column]:
error_dict = {}
error_dict["header"] = column
error_dict[
"line_number"] = line_number + 1 #0 Indexed with 0 being the header row
error_dict["error_string"] = str(
my_validator.failures[column][line_number])
errors_list.append(error_dict)
for missing_field in my_validator.missing_fields:
error_dict = {}
error_dict["header"] = "Missing Header"
error_dict["line_number"] = "N/A"
error_dict["error_string"] = "Missing column %s" % (missing_field)
errors_list.append(error_dict)
valid_rows = []
row_count = 0
#Read in the good rows
try:
no_validation_lines = [
int(error["line_number"]) for error in errors_list
]
row_count = 0
with open(filename) as csvfile:
reader = csv.DictReader(csvfile, delimiter="\t")
for row in reader:
row_count += 1
if row_count in no_validation_lines:
continue
valid_rows.append(row)
except:
#raise
print("error reading file")
return passes_validation, my_validator.failures, errors_list, valid_rows, row_count
def test_float_validator_fails(field):
with pytest.raises(ValidationException):
FloatValidator().validate(field)
def test_float_validator_works(field):
FloatValidator().validate(field)